CVPR 2023 - Vancouver, Canada

C3DV: 1st Workshop on Compositional 3D Vision

First workshop on compositional 3D vision and 3DCoMPaT dataset challenge, hosted by #CVPR2023.

000

Days

00

Hours

00

Minutes

00

Secondes

Challenge

3DCoMPaT Challenge

Challenge overview


The Grounded CoMPaT Recognition (GCR) is a compositional 3D vision task that aims to collectively recognize and ground compositions of materials on parts of 3D objects. This task is based on the 3DCoMPaT dataset, a large-scale dataset composed of stylized 3D objects and associated 2D renderings.
We propose two variations of this task: GCR-Coarse and GCR-Fine, which are based on coarse-grained and fine-grained 3D segmentations of the 3DCoMPaT models.
We highly encourage participants of the challenge to enter and submit to both tracks of the challenge.

Dataset


The 3DCoMPaT dataset for both challenge tracks will be made available soon.

Submission


Submission links on CodaLab for both tracks will be made available soon, which will include detailed instructions and evaluation criteria.

Rules


TBA.

Awards


TBA.

Q&A


If you encounter any technical issue related to the challenge, or if you're missing critical information, please open a ticket on our GitHub repository.

Paper submission

Call for papers

Topics


Besides the CoMPaT challenge, the C3DV workshop also accepts papers in relation with compositional 3D vision. The workshop will include a poster and an oral session for related works. Topics of this workshop include but are not limited to:

  • Deep learning methods for compositional 3D vision
  • Self-supervised learning for compositional 3D vision
  • Visual relationship detection in 3D scenes
  • Zero-shot recognition/detection of compositional 3D visual concepts
  • Novel problems in 3D vision and compositionality
  • Text/composition to 3D generation
  • Text/composition-based editing of 3D scenes/objects
  • Language-guided 3D visual understanding (objects, relationships, ...)
  • Transfer learning for compositional 3D Vision
  • Multimodal pre-training for 3D understanding
  • ...

The submitted 4-page abstracts will be peer-reviewed in CVPR format. Abstracts will be presented in the workshop poster session, and a portion of the accepted papers will be orally presented.

Submission


Paper submissions will be handled with CMT through the following link:

Microsoft CMT: C3DV-2023

Please select the appropriate track (archival or non-archival) and check for the relevant timelines in the dates section.

Paper awards


TBA.

Speakers

Invited Speakers

Jitendra Malik

Professor University of California, Berkeley

Georgia Gkioxari

Assistant Professor California Institute of Technology

Katerina Fragkiadaki

Assistant Professor Carnegie Mellon University

Matthias Nie├čner

Professor Technical University of Munich

Angel Xuan Chang

Assistant Professor Simon Fraser University

Organizers

Workshop Organizers

Wolfgang Heidrich

Professor KAUST

Peter Vajda

Researcher and Engineering Manager Meta AI

Natalia Neverova

Research Lead Meta AI

Mohamed Elhoseiny

Assistant Professor KAUST

Challenge Organizers

Habib Slim

Ph.D. Student KAUST

Yuchen Li

Ph.D. Student KAUST

Xiang Li

Postdoctoral Researcher KAUST

Peter Wonka

Professor KAUST

Mohamed Elhoseiny

Assistant Professor KAUST

Dates

Timeline

Archival track (will appear in CVPR proceedings):
Event Date
Paper submission deadline March 17, 2023 - 11:59 PM PT
Notification to authors March 31, 2023
Camera-ready deadline April 7, 2023
Workshop date June 18, 2023
Non-archival track:
Event Date
Paper submission deadline May 1, 2023
Notification to authors May 20, 2023
Camera-ready deadline June 5, 2023
Workshop date June 18, 2023
Event Date
Release of training/validation data March 21, 2023
Validation server online March 31, 2023
Test server online April 1, 2023
Submission deadline April 20, 2023
Fact sheets/source code submission deadline April 31, 2023
Winners announcement TBA.

Program

Workshop Program

The workshop program has not been announced yet. Stay tuned!


The workshop will cover:

  • A talk for each keynote speaker
  • A presentation of the 3DCoMPaT challenge
  • A presentation from the winners of the challenge
  • A panel discussion

Please stay tuned for the announcement of the definitive program.

For any question or support, please reach @Habib.S. Background image courtesy of @Adi.K.